@inproceedings{shafieibavani-etal-2018-graph,
title = "A Graph-theoretic Summary Evaluation for {ROUGE}",
author = "ShafieiBavani, Elaheh and
Ebrahimi, Mohammad and
Wong, Raymond and
Chen, Fang",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1085",
doi = "10.18653/v1/D18-1085",
pages = "762--767",
abstract = "ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate summaries including lexical variations and paraphrasing. We propose a graph-based approach adopted into ROUGE to evaluate summaries based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets show that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shafieibavani-etal-2018-graph">
<titleInfo>
<title>A Graph-theoretic Summary Evaluation for ROUGE</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elaheh</namePart>
<namePart type="family">ShafieiBavani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate summaries including lexical variations and paraphrasing. We propose a graph-based approach adopted into ROUGE to evaluate summaries based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets show that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments.</abstract>
<identifier type="citekey">shafieibavani-etal-2018-graph</identifier>
<identifier type="doi">10.18653/v1/D18-1085</identifier>
<location>
<url>https://aclanthology.org/D18-1085</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>762</start>
<end>767</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Graph-theoretic Summary Evaluation for ROUGE
%A ShafieiBavani, Elaheh
%A Ebrahimi, Mohammad
%A Wong, Raymond
%A Chen, Fang
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F shafieibavani-etal-2018-graph
%X ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate summaries including lexical variations and paraphrasing. We propose a graph-based approach adopted into ROUGE to evaluate summaries based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets show that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments.
%R 10.18653/v1/D18-1085
%U https://aclanthology.org/D18-1085
%U https://doi.org/10.18653/v1/D18-1085
%P 762-767
Markdown (Informal)
[A Graph-theoretic Summary Evaluation for ROUGE](https://aclanthology.org/D18-1085) (ShafieiBavani et al., EMNLP 2018)
ACL
- Elaheh ShafieiBavani, Mohammad Ebrahimi, Raymond Wong, and Fang Chen. 2018. A Graph-theoretic Summary Evaluation for ROUGE. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 762–767, Brussels, Belgium. Association for Computational Linguistics.